Yongtao Wu

Research Interests

Deep learning
Over-parametrized models

Biography

Yongtao Wu received a Bachelor’s degree inTelecommunication Engineering from Sun Yat-sen University in 2020, and a Master’s degree in Machine Learning from KTH Royal Institute of Technology in 2022. From July to September 2022 he was an intern at LIONS. In September 2022 he started his PhD at LIONS.

Publications

Robust NAS under adversarial training: benchmark, theory, and beyond

2024. 12th International Conference on Learning Representations (ICLR 2024).

Detailed record

Revisiting Character-level Adversarial Attacks for Language Models

2024. 41st International Conference on Machine Learning (ICML 2024).

Detailed record

On the Convergence of Encoder-only Shallow Transformers

2023. 37th Annual Conference on Neural Information Processing Systems.

Detailed record

Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study

2022. 36th Conference on Neural Information Processing Systems (NeurIPS).

Detailed record

Contact

EPFL people page